1 code implementation • 28 Mar 2024 • Niklas Stoehr, Mitchell Gordon, Chiyuan Zhang, Owen Lewis
Can we localize the weights and mechanisms used by a language model to memorize and recite entire paragraphs of its training data?
no code implementations • ICLR Workshop LLD 2019 • Owen Lewis, Katherine Hermann
We address the problem of teaching an RNN to approximate list-processing algorithms given a small number of input-output training examples.